Emanuele Rodolà is Full Professor of Computer Science at Sapienza University of Rome, where he leads the GLADIA group of Geometry, Learning and Applied AI, funded by an ERC Grant and a Google Research Award, and acts as the Director of the PhD in Computer Science. Previously, he was Assistant and then Associate Professor at Sapienza (2017-2020), a postdoc at USI Lugano (2016-2017), an Alexander von Humboldt Fellow at TU Munich (2013-2016), and a JSPS Research Fellow at The University of Tokyo (2013). He is an ELLIS fellow and a fellow of the Young Academy of Europe, has received a number of research prizes, has been serving in the program and organizing committees of the top rated conferences in computer vision, machine learning and graphics, founded and chaired several successful workshops. His research interests lie at the intersection of geometry processing, graph and geometric deep learning, computer vision, language and signal processing, and has published more than 100 papers in these areas.
You can find the full CV at this link.
Interests
- Artificial Intelligence
- Geometry Processing
- Graph and Geometric Deep Learning
- ML for Audio
- Computer Vision
Latest
- Multi-Source Diffusion Models for Simultaneous Music Generation and Separation
- SyncFusion: Multimodal Onset-synchronized Video-to-Audio Foley Synthesis
- Generalized Multi-Source Inference for Text Conditioned Music Diffusion Models
- Vector Quantile Regression on Manifolds
- Paper accepted as Oral at ICLR 2024
- ASIF: Coupled Data Turns Unimodal Models to Multimodal Without Training
- Latent Space Translation via Semantic Alignment
- From Bricks to Bridges: Product of Invariances to Enhance Latent Space Communication
- Continuous Vector Quantile Regression
- Papers accepted at NeurIPS 2023
- Geometric Epitope and Paratope Prediction
- Accelerating Transformer Inference for Translation via Parallel Decoding
- Multimodal Neural Databases
- Bootstrapping Parallel Anchors for Relative Representations
- Latent Autoregressive Source Separation
- Spectral Maps for Learning on Subgraphs
- Metric Based Few-Shot Graph Classification
- Certification of Gaussian Boson Sampling via graphs feature vectors and kernels
- 3D Human Pose Estimation Using Möbius Graph Convolutional Networks
- Relative representations enable zero-shot latent space communication
- Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
- Multimodal Feature Fusion and Knowledge-Driven Learning via Experts Consult for Thyroid Nodule Classification
- Learning Spectral Unions of Partial Deformable 3D Shapes
- 3D Shape Analysis Through a Quantum Lens: the Average Mixing Kernel Signature
- Explanatory learning: Beyond empiricism in neural networks
- Fish sounds: towards the evaluation of marine acoustic biodiversity through data-driven audio source separation
- KiloNeuS: A Versatile Neural Implicit Surface Representation for Real-Time Rendering
- Localized Shape Modelling with Global Coherence: An Inverse Spectral Approach
- MoMaS: Mold Manifold Simulation for real-time procedural texturing
- Neural Implicit Style-net: synthesizing shapes in a preferred style exploiting self supervision
- Newton’s Fractals on Surfaces via Bicomplex Algebra
- Reduced Representation of Deformation Fields for Effective Non-rigid Shape Matching
- Sparse Vicious Attacks on Graph Neural Networks
- Learning disentangled representations via product manifold projection
- Spectral Shape Recovery and Analysis via Data-driven Connections
- Shape registration in the time of transformers
- Cluster-driven Graph Federated Learning over Multiple Domains
- Universal Spectral Adversarial Attacks for Deformable Shapes
- Efficiently parallelizable strassen-based multiplication of a matrix by its transpose
- Orthogonalized Fourier polynomials for signal approximation and transfer
- Unsupervised source separation via Bayesian inference in the latent domain
- Wavelet-based Heat Kernel Derivatives: Towards Informative Localized Shape Analysis
- Instant recovery of shape from spectrum via latent space connections
- Nonlinear Spectral Geometry Processing via the TV Transform
- 2D Skeleton-Based Action Recognition via Two-Branch Stacked LSTM-RNNs
- Towards Precise Completion of Deformable Shapes
- FARM: Functional automatic registration method for 3D human bodies
- A parametric analysis of discrete Hamiltonian functional maps
- Deciphering interaction fingerprints from protein molecular surfaces using geometric deep learning
- Generating Adversarial Surfaces via Band-Limited Perturbations
- LIMP: Learning Latent Shape Representations with Metric Preservation Priors
- Learning interaction patterns from surface representations of protein structure
- ZoomOut: Spectral Upsampling for Efficient Shape Correspondence
- Correspondence-Free Region Localization for Partial Shape Similarity via Hamiltonian Spectrum Alignment
- High-Resolution Augmentation for Automatic Template-Based Matching of Human Models
- GFrames: Gradient-based local reference frame for 3D shape matching
- Unsupervised learning of dense shape correspondence
- SHREC'19: Matching humans with different connectivity
- SHREC'19: Shape Correspondence with Isometric and Non-Isometric Deformations
- Functional maps representation on product manifolds
- Isospectralization, or how to hear shape, style, and correspondence
- Localized manifold harmonics for spectral shape analysis
- Improved functional mappings via product preservation
- Efficient 2D-to-3D deformable shape matching for 3D shape retrieval applications
- Partial Single- and Multishape Dense Correspondence Using Functional Maps
- Spatial Maps: From low rank spectral to sparse spatial functional representations
- Regularized Point-wise Map Recovery from Functional Correspondence
- Deep Functional Maps: Structured Prediction for Dense Shape Correspondence
- Efficient deformable shape correspondence via kernel matching
- Geometric deep learning on graphs and manifolds using mixture model CNNs
- Product Manifold Filter: Non-rigid shape correspondence via kernel density estimation in the product space
- Fully spectral partial shape matching
- SHREC'17: Deformable shape retrieval with missing parts
- Computing and Processing Correspondences with Functional Maps
- Consistent Partial Matching of Shape Collections via Sparse Modeling
- Partial Functional Correspondence
- A Game-theoretical Approach for Joint Matching of Multiple Feature throughout Unordered Images
- An Accurate and Robust Artificial Marker Based on Cyclic Codes
- Learning shape correspondence with anisotropic convolutional neural networks
- Coupled functional maps
- Shape analysis with anisotropic windowed Fourier transform
- Non-rigid puzzles
- Efficient globally optimal 2d-to-3d deformable shape matching
- Anisotropic Diffusion Descriptors
- SHREC'16: Matching of deformable shapes with topological noise
- Applying Random Forests to the Problem of Dense Non-Rigid Shape Correspondence
- Computing and Processing Correspondences with Functional Maps
- Geometric Deep Learning
- Matching deformable objects in clutter
- SHREC'16: Partial matching of deformable shapes
- Point-wise map recovery and refinement from functional correspondence
- Realistic Photometric Stereo Using Partial Differential Irradiance Equation Ratios
- A Simple and Effective Relevance-Based Point Sampling for 3D Shapes
- Fast and Accurate Surface Alignment Through an Isometry-Enforcing Game
- Adopting an unconstrained ray model in light-field cameras for 3D shape reconstruction
- Analysis of surface parametrizations for modern photometric stereo modeling
- Learning similarities for rigid and non-rigid object detection
- Anisotropic Laplace-Beltrami operators for shape analysis
- Optimal Intrinsic Descriptors for Non-Rigid Shape Analysis
- Robust Region Detection via Consensus Segmentation of Deformable Shapes
- Dense non-rigid shape correspondence using random forests
- Elastic net constraints for shape matching
- Efficient Shape Matching using Vector Extrapolation.
- Can a fully unconstrained imaging model be applied effectively to central cameras?
- Stable and Fast Techniques for Unambiguous Compound Phase Coding
- A Scale Independent Selection Process for 3D Object Recognition in Cluttered Scenes
- A Game-Theoretic Approach to Pairwise Clustering and Matching
- A game-theoretic approach to deformable shape matching
- Imposing Semi-local Geometric Constraints for Accurate Correspondences Selection in Structure from Motion: a Game-Theoretic Perspective
- Multiview registration via graph diffusion of dual quaternions
- Rune-tag: A high accuracy fiducial marker with strong occlusion resilience
- A Non-Cooperative Game for 3D Object Recognition in Cluttered Scenes
- Sampling relevant points for surface registration
- Loosely distinctive features for robust surface alignment
- A Game-Theoretic Approach to Robust Selection of Multi-View Point Correspondence
- A game-theoretic approach to the enforcement of global consistency in multi-view feature matching
- Robust camera calibration using inaccurate targets
- Robust figure extraction on textured background: a game-theoretic approach
- A game-theoretic approach to fine surface registration without initial motion estimation
- Robust game-theoretic inlier selection for bundle adjustment
- Fast 3D surface reconstruction by unambiguous compound phase coding